Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.0662. Min Range: -3.0662

Max Act: 3.0662. Min Act: -0.1700

Data Index: 5154677 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8845. Min Act: -0.1700

Data Index: 2558254 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8519. Min Act: -0.1700

Data Index: 8602378 (Open Web Text)

Max Activating Token Index: 271

Text #3

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8326. Min Act: -0.1700

Data Index: 1559306 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8145. Min Act: -0.1700

Data Index: 6554584 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8202. Min Act: -0.1700

Data Index: 7338671 (Open Web Text)

Max Activating Token Index: 431

Text #6

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8241. Min Act: -0.1700

Data Index: 3471836 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8006. Min Act: -0.1700

Data Index: 3097206 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8006. Min Act: -0.1700

Data Index: 5450592 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8113. Min Act: -0.1700

Data Index: 7885989 (Open Web Text)

Max Activating Token Index: 916

Text #10

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8069. Min Act: -0.1700

Data Index: 2427729 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7819. Min Act: -0.1700

Data Index: 166033 (Open Web Text)

Max Activating Token Index: 445

Text #12

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8010. Min Act: -0.1700

Data Index: 7021274 (Open Web Text)

Max Activating Token Index: 137

Text #13

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7750. Min Act: -0.1700

Data Index: 3310866 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7843. Min Act: -0.1700

Data Index: 4735587 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7412. Min Act: -0.1700

Data Index: 147363 (Open Web Text)

Max Activating Token Index: 482

Text #16

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7441. Min Act: -0.1700

Data Index: 1846348 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7523. Min Act: -0.1700

Data Index: 4761003 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7608. Min Act: -0.1700

Data Index: 7821411 (Open Web Text)

Max Activating Token Index: 936

Text #19

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7561. Min Act: -0.1700

Data Index: 1719380 (Open Web Text)

Max Activating Token Index: 860